Interpreting Machine Learning Pipelines Produced by Evolutionary AutoML for Biochemical Property Prediction

Created by W.Langdon from gp-bibliography.bib Revision:1.8528

@InProceedings{de-sa:2025:GECCOcomp,

• author = "Alex G. C. {de Sa} and Gisele L. Pappa and Alex A. Freitas and David B. Ascher",
• title = "Interpreting Machine Learning Pipelines Produced by Evolutionary {AutoML} for Biochemical Property Prediction",
• booktitle = "Evolutionary Computation and Explainable AI",
• year = "2025",
• editor = "Jaume Bacardit and Alexander Brownlee and Stefano Cagnoni and Giovanni Iacca and John McCall and David Walker",
• pages = "1944--1952",
• address = "Malaga, Spain",
• series = "GECCO '25 Companion",
• month = "14-18 " # jul,
• organisation = "SIGEVO",
• publisher = "Association for Computing Machinery",
• publisher_address = "New York, NY, USA",
• keywords = "genetic algorithms, genetic programming, automated machine learning (AutoML), cheminformatics, drug discovery, AutoML-generated pipeline interpretability, Bayesian networks, XAI",
• isbn13 = "979-8-4007-1464-1",
• URL = "https://doi.org/10.1145/3712255.3734339",
• DOI = "doi:10.1145/3712255.3734339",
• size = "9 pages",
• abstract = "Machine learning (ML) has been playing a crucial role in drug discovery, mainly through quantitative structure-activity relationship models that relate molecular structures to properties, such as absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties. However, traditional ML approaches often lack customisation to a particular biochemical task and fail to generalise to new biochemical spaces, resulting in reduced predictive performance. Automated machine learning (AutoML) has emerged to address these limitations by automatically selecting the suitable ML pipelines for a given input dataset. Despite its potential, AutoML is underused in cheminformatics, and its decisions often lack interpretability, reducing user trust - especially among non-experts. Accordingly, this paper proposes an evolutionary AutoML method for biochemical property prediction that outputs an interpretable model for understanding the evolved ML pipelines. It combines grammar-based genetic programming with Bayesian networks to guide search and enhance the searched pipelines' interpretability. The evaluation on 12 benchmark ADMET datasets showed that the proposed AutoML method obtained similar or better results than three existing methods. Additionally, the interpretable Bayesian network identified, among the ML pipelines' components generated by the AutoML method (i.e. components like biochemical feature extraction methods, preprocessing techniques and ML algorithms), which components affect the ML pipelines' predictive performance.",
• notes = "GECCO-2025 ECXAI workshop A Recombination of the 34th International Conference on Genetic Algorithms (ICGA) and the 30th Annual Genetic Programming Conference (GP)",

}

Genetic Programming entries for Alex G C de Sa Gisele L Pappa Alex Alves Freitas David B Ascher

Citations